© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18456
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific people or places

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    235
    +0.11
    0.5%
    612
    +0.11
    0.5%
    167
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.11
    0.05
    610
    +0.11
    0.03
    454
    +0.11
    0.04
    Negative Logits
     srfAttach
    -0.72
     erection
    -0.65
    INGTON
    -0.62
     Jr
    -0.61
    undo
    -0.61
     XIII
    -0.60
    ENSE
    -0.60
    vernment
    -0.59
    VERTIS
    -0.59
    emetery
    -0.59
    POSITIVE LOGITS
    pher
    1.57
    athed
    1.39
    pherd
    1.36
    athing
    1.35
    pard
    1.34
    ffield
    1.34
    ldon
    1.25
    ikh
    1.21
    lled
    1.16
    bang
    1.14
    Activations Density 0.083%

    No Known Activations